<![CDATA[This study aims to estimate the movement of the Indonesia Composite Stock Price Index (IHSG) using linear regression and Ridge Regression based on monthly data from 2010 to 2024, where IHSG serves as a key indicator of Indonesia’s capital market and requires a simple yet reliable estimation model to support economic and investment decisions. The methodology applies linear regression as a baseline model and Ridge Regression to address potential multicollinearity among independent variables, with model performance evaluated using 5-fold cross-validation and metrics including Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The results show that linear regression achieves MAE = 0.068829, MSE = 0.007987, and RMSE = 0.087823, while Ridge Regression performs slightly better with MAE = 0.068547, MSE = 0.007970, and RMSE = 0.087732. Although the differences are relatively small, Ridge Regression consistently produces lower and more stable error values, indicating that it is a more robust alternative for IHSG estimation, particularly for medium- to long-term analysis.]]>
Copyrights © 2026
